]> jfr.im git - yt-dlp.git/blame - youtube_dl/extractor/mlb.py
[crackled] Improve, fix invalid regexes and extract more metadata
[yt-dlp.git] / youtube_dl / extractor / mlb.py
CommitLineData
b1b01841
CC
1from __future__ import unicode_literals
2
3import re
4
5from .common import InfoExtractor
7bb49d10
S
6from ..utils import (
7 parse_duration,
8 parse_iso8601,
9 find_xpath_attr,
10)
b1b01841
CC
11
12
7bb49d10
S
13class MLBIE(InfoExtractor):
14 _VALID_URL = r'http?://m\.mlb\.com/video/(?:topic/[\da-z_-]+/)?v(?P<id>n?\d+)'
15 _TESTS = [
16 {
17 'url': 'http://m.mlb.com/video/topic/81536970/v34496663/mianym-stanton-practices-for-the-home-run-derby',
18 'md5': 'd9c022c10d21f849f49c05ae12a8a7e9',
19 'info_dict': {
20 'id': '34496663',
21 'ext': 'mp4',
22 'title': 'Stanton prepares for Derby',
23 'description': 'md5:d00ce1e5fd9c9069e9c13ab4faedfa57',
24 'duration': 46,
25 'timestamp': 1405105800,
26 'upload_date': '20140711',
27 'thumbnail': 're:^https?://.*\.jpg$',
28 },
b1b01841 29 },
7bb49d10
S
30 {
31 'url': 'http://m.mlb.com/video/topic/vtp_hrd_sponsor/v34578115/hrd-cespedes-wins-2014-gillette-home-run-derby',
32 'md5': '0e6e73d509321e142409b695eadd541f',
33 'info_dict': {
34 'id': '34578115',
35 'ext': 'mp4',
36 'title': 'Cespedes repeats as Derby champ',
37 'description': 'md5:08df253ce265d4cf6fb09f581fafad07',
38 'duration': 488,
39 'timestamp': 1405399936,
40 'upload_date': '20140715',
41 'thumbnail': 're:^https?://.*\.jpg$',
42 },
43 },
44 {
45 'url': 'http://m.mlb.com/video/v34577915/bautista-on-derby-captaining-duties-his-performance',
46 'md5': 'b8fd237347b844365d74ea61d4245967',
47 'info_dict': {
48 'id': '34577915',
49 'ext': 'mp4',
50 'title': 'Bautista on Home Run Derby',
51 'description': 'md5:b80b34031143d0986dddc64a8839f0fb',
52 'duration': 52,
53 'timestamp': 1405390722,
54 'upload_date': '20140715',
55 'thumbnail': 're:^https?://.*\.jpg$',
56 },
57 },
58 ]
b1b01841
CC
59
60 def _real_extract(self, url):
61 mobj = re.match(self._VALID_URL, url)
62 video_id = mobj.group('id')
63
7bb49d10
S
64 detail = self._download_xml(
65 'http://m.mlb.com/gen/multimedia/detail/%s/%s/%s/%s.xml'
66 % (video_id[-3], video_id[-2], video_id[-1], video_id), video_id)
67
68 title = detail.find('./headline').text
69 description = detail.find('./big-blurb').text
70 duration = parse_duration(detail.find('./duration').text)
71 timestamp = parse_iso8601(detail.attrib['date'][:-5])
72
73 thumbnail = find_xpath_attr(
74 detail, './thumbnailScenarios/thumbnailScenario', 'type', '45').text
b1b01841 75
7bb49d10
S
76 formats = []
77 for media_url in detail.findall('./url'):
78 playback_scenario = media_url.attrib['playback_scenario']
79 fmt = {
80 'url': media_url.text,
81 'format_id': playback_scenario,
82 }
83 m = re.search(r'(?P<vbr>\d+)K_(?P<width>\d+)X(?P<height>\d+)', playback_scenario)
84 if m:
85 fmt.update({
86 'vbr': int(m.group('vbr')) * 1000,
87 'width': int(m.group('width')),
88 'height': int(m.group('height')),
89 })
90 formats.append(fmt)
172240c0 91
7bb49d10 92 self._sort_formats(formats)
172240c0 93
b1b01841
CC
94 return {
95 'id': video_id,
b1b01841 96 'title': title,
b1b01841 97 'description': description,
7bb49d10
S
98 'duration': duration,
99 'timestamp': timestamp,
100 'formats': formats,
b1b01841
CC
101 'thumbnail': thumbnail,
102 }